检索结果-内蒙古大学图书馆

6th IEEE conference on Energy internet and Energy System Integration, EI2 2022

作者： Jiang, Yixin Zhang, Yunan Kuang, Xiaoyun Xu, Aidong Dong, Xuzhu Dai, Shiyong Huang, Jinhua Electric Power Research Institute CSG Guangzhou China Guangdong Provincial Key Laboratory of Power System Network Security Guangzhou China Wuhan University School of Electrical Engineering China Joint Laboratory on Cyberspace Security CSG Guangzhou China

ISBN: (纸本)9798350347159

Industrial control network intrusion detection system has higher requirements for detection rate, false positive rate, and real-time performance. In order to solve this problem, this paper proposed a new type of feature extractor abstracting mapping from the original low-level feature set to the high-level feature set. This feature extractor is composed of 3 heterogeneous sub-feature extractors 1D CNN, LSTM, and SAE. Secondly, the integrated feature set passes through a random forest (RF) classifier. Thirdly, combined with the regularity and stability of the industrial control network, a suspected host inspection method is designed based on the sequential hypothesis testing of real-time network traffic. This method uses the individual learner results of the above 3 feature extractors. Combining the above, two-stage fusion (SHT-RF) is carried out to realize real-time industrial control network intrusion detection, and achieve the purpose of improving the detection rate and enhancing the robustness of the system. Finally, it is verified on the CICIDS2017 data set. The detection rate of the proposed method is 99.59%, and the false positive rate is 0.09%. Compared with other machine learning methods, it has achieved a good improvement effect. © 2022 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

A sparse regularized soft sensor based on GRU and self-interpretation double nonnegative garrote: From variable selection to structure optimization

引用

control ENGINEERING PRACTICE 2024年 153卷

作者： Sui, Lin Sun, Wenxin Liu, Wentao Xiong, Weili Jiangnan Univ Sch Internet Things Engn Key Lab Adv Proc Control Light Ind Minist Educ Wuxi 214122 Peoples R China

Soft sensors, as a significant paradigm for industrial intelligence, are extensively utilized in large-scale industrial integration systems to estimate the pivotal quality variables. For deep neural network-based soft sensors, redundancy in input variables and network structure has emerged as one of the most important challenges. In this article, a sparse regularized soft sensor based on the gated recurrent unit (GRU) and self- interpretation dual nonnegative garrote is proposed. Initially, a proficiently trained GRU network is established as the pre-trained model, followed by the design of a set of self-interpretation factors based on the mean influence value of different input variables. Secondly, the contraction coefficients of the nonnegative garrote are sequentially incorporated into the GRU input and hidden layer weight matrices. Meanwhile, the self- interpretation factors are introduced into the constraints of the nonnegative garrote algorithm to guide it to adaptively adjust the applied penalty strength based on the relative importance of different input variables. The strategy integrates variable selection with the model training process to sparsify the network structure and provide self-interpretable variable selection results. Finally, the performance of the developed approach is verified through a practical application in power plant desulfurization systems. The case studies demonstrate that the developed approach for soft sensor modeling outperforms other existing methods and shows promising application prospects. In addition, the validity of the self-interpretable variable selection results is verified via the known mechanism analysis and expert experience.

关键词： Soft sensors Nonnegative garrote Gated recurrent unit Variable selection network structure optimization Large-scale industrial systems

来源：评论

学校读者我要写书评

暂无评论

HCMM: Adaptive Modeling and Scheduling Mechanism for Satellite internet Test Platform 9

HCMM: Adaptive Modeling and Scheduling Mechanism for Satelli...

引用

9th International conference on Communication and Information Processing, ICCIP 2023

作者： Ni, Nannan Liu, Yaoqi Zhou, Yiqing Li, Hongguang Zhou, Xianlin Ren, Pingping Zhengzhou University Henan Institute of Advanced Technology Zhengzhou450001 China Zhongke Nanjing Mobile Communication & Computing Innovation Institute Nanjing211135 China Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China State Key Lab of processors Institute of Computing Technology CAS Beijing100190 China Information Technology Co. Ltd. Nanjing Branch Nanjing210000 China

ISBN: (纸本)9798400708909

Low-Earth-Orbit Satellite Constellation network (LEO-SCN) can provide low-cost, large-scale, flexible coverage of wireless communications services. Simulation demonstration is significant for high-cost, high-dynamic, and large-scale LEO-SCN systems. Therefore, the performance evaluation of satellite internet can be carried out using the integrated information network integrated test and test platform (super simulation, emulation, and Test bed, S-SET). In this paper, a Hybrid Communication Mechanism Middleware (HCMM) is designed for providing efficient and high-speed data exchange between S-SET and other algorithm models and frameworks. HCMM stores and transmits each simulated entity's status and control information in the simulation environment, enabling a large amount of data interaction between S-SET and other algorithmic models and frameworks. Experiments show that this middleware can take into account both efficiency and security, especially for use cases where a large amount of data must be transferred between S-SET and artificial intelligence framework. The user can flexibly select the communication mechanism according to the deployment scheme, and the IPC transmission speed can be increased by about 20 times on stand-alone deployment. This middleware can effectively promote the research of model algorithms in LEO-SCN, provide middleware to solve the language barrier between simulation platforms and artificial intelligence algorithms, and promote the development of related technologies of giant LEO-SCN. © 2023 Copyright held by the owner/author(s)

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

Lagrange Coded Federated Learning (L-CoFL) Model for internet of Vehicles 42

Lagrange Coded Federated Learning (L-CoFL) Model for Interne...

引用

42nd IEEE International conference on Distributed Computing systems (ICDCS)

作者： Ni, Weiquan Zhu, Shaoliang Karim, Md Monjurul Asheralieva, Alia Kang, Jiawen Xiong, Zehui Maple, Carsten Southern Univ Sci & Technol Dept Comp Sci & Engn Shenzhen Peoples R China Southern Univ Sci & Technol Res Inst Trustworthy Autonomous Syst Shenzhen Peoples R China Guangdong Univ Technol Sch Automat Guangzhou Peoples R China Singapore Univ Technol & Design Pillar Informat Syst Technol & Design Singapore Singapore Univ Warwick WMG Coventry W Midlands England

ISBN: (数字)9781665471770

ISBN: (纸本)9781665471770

In internet-of-Vehicles (IoV), smart vehicles can efficiently process various sensing data through federated learning (FL) - a privacy-preserving distributed machine learning (ML) approach that allows collaborative development of the shared ML model without any data exchange. However, traditional FL approaches suffer from poor security against the system noise, e.g., due to low-quality trained data, wireless channel errors, and malicious vehicles generating erroneous results, which affects the accuracy of the developed ML model. To address this problem, we propose a novel FL model based on the concept of Lagrange coded computing (LCC) - a coded distributed computing (CDC) scheme that enables enhancing the system security. In particular, we design the first L-CoFL (Lagrange coded FL) model to improve the accuracy of FL computations in the presence of low-quality trained data and wireless channel errors, and guarantee the system security against malicious vehicles. We apply the proposed L-CoFL model to predict the traffic slowness in IoV and verify the superior performance of our model through extensive simulations.

关键词： Coded distributed computing (CDC) data privacy federated learning internet of Vehicles (IoV) machine learning security

来源：评论

学校读者我要写书评

暂无评论

A network security situational awareness system for text classification 2

A network security situational awareness system for text cla...

引用

2022 2nd International conference on Power System and Energy internet, PoSEI 2022

作者： Pang, Xiaojian Su, Yang Tao, Wenwei Hu, Zhaohui Chen, Haiguang China Southern Power Grid Power Dispatching Control Center Guangdong Guangzhou China China Southern Power Grid Digital Grid Research Institute Co. Ltd. Guangdong Guangzhou China

The evaluation function of the existing network security situational awareness system is not perfect and often causes large average absolute errors. Therefore, a network security situational awareness system for text classification is designed. The hardware part selects the sensor main control chip and connects the circuit power supply to ensure the safe and stable operation of the whole system. In the software part, the data packet information is collected and processed to remove the data noise, and the information extraction technology is used to construct the classification model of this paper. The network abnormal behavior is identified according to the host log, the data characteristics of security behavior are extracted, and the system module evaluation function is set according to the extraction results. The experimental results show that the average absolute error of the designed system is less than that of the other three existing systems, and the performance of the security situational awareness system is better. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： network security

来源：评论

学校读者我要写书评

暂无评论

Research on Temperature and Humidity Prediction Model of High Voltage Switchgear Based on SSA-BP Algorithm 4

Research on Temperature and Humidity Prediction Model of Hig...

引用

4th International conference on Smart Power and internet Energy systems (SPIES)

作者： Shen Genqiang Zhang Longchao Zhu Jiyun Xu Min Zhu Mengzhou Chong Pei State Grid Zhejiang Elect Power Co Ltd Huzhou Power Supply Co Huzhou Zhejiang Peoples R China China Three Gorges Univ Coll Elect Engn & New Energy Yichang Peoples R China

ISBN: (纸本)9781665489577

Moisture and condensation in high voltage switchgear will cause corrosion of parts, degradation of insulation performance and surface discharge. At the same time, the change of temperature and humidity inside the high-voltage switchgear has the characteristics of time sequence, nonlinear, spatial distribution difference and so on, which will lead to the hysteresis of the response of the dehumidification control system. Therefore, the high voltage switchgear temperature and humidity prediction model to predict the temperature and humidity in the switchgear was establishes in this paper. A prediction model of temperature and humidity in high voltage switchgear based on Sparrow Search Algorithm (SSA) and Back Propagation (BP) is proposed. Firstly, the quantifiable factors affecting the temperature and humidity of the switch cabinet are analyzed. Then the temperature and humidity prediction model of high voltage switchgear based on SSA-BP is constructed. Finally, a data acquisition system is built to obtain the input and output data of the model, and the prediction model is trained and verified. In this paper, the performance of BP, PSO-BP, GA-BP and SSA-BP prediction models are compared by the degree of correlation fitting and error interval ratio between predicted and actual temperature and humidity values. Then, the root mean square error (RMSE), mean absolute error (MAE), mean relative error (MAPE), and coefficient of determination (R2) were used to quantitatively compare and analyze the four prediction models. The results show that, compared with BP prediction model, PSO-BP prediction model and GA-BP prediction model, SSA-BP prediction model has the best prediction effect, and can better predict the temperature and humidity inside the electric cabinet.

关键词： high voltage switchgear Temperature and humidity prediction BP neural network Sparrow search algorithm (SSA) safe operation

来源：评论

学校读者我要写书评

暂无评论

Stochastic network Calculus Based quality of Service Guarantee for Multi-class Traffic

Stochastic Network Calculus Based Quality of Service Guarant...

引用

IEEE International conference on performance, Computing and Communications (IPCCC)

作者： Yunlan Wang Qing Wang Tianhai Zhao YongKuo Hu JianHua Gu ZhengXiong Hou Northwestern Polytechnical University Xi’an China

ISBN: (数字)9798350367942

ISBN: (纸本)9798350367959

With the rapid development of cloud computing technology, a variety of emerging network traffic types have higher quality of service(QoS) requirements. However, the traditional internet’s best-effort service cannot meet the demands of cloud computing applications. Therefore, we propose a stochastic network calculus(SNC) based QoS guarantee mechanism consisting of two parts. The first part is MTACC, a multi-threshold adaptive admission control algorithm based on network calculus. MTACC classifies network traffic, calculates resource requirements, and introduces admission probabilities and demarcation parameters. As the network load reaches various thresholds, MTACC adjusts the demarcation parameter to modify the admission probabilities accordingly. The second part is TSRA, a two-stage resource allocation algorithm. In the first stage, basic resources are allocated to ensure the minimum resource requirements of the network traffic based on SNC. In the second stage, additional idle resources are allocated to improve the QoS of the network traffic based on the resource utility function. Finally, we simulate the QoS guarantee techniques using NS3. By comparing with Simple Sum and SCAC, we verify the effectiveness of our proposed QoS guarantee techniques. They provide robust performance guarantees for multi-class traffic such as delay-sensitive, bandwidth-sensitive, and packet loss-sensitive traffic.

关键词： Computers Cloud computing Admission control Telecommunication traffic Bandwidth Probability Calculus Classification algorithms Resource management Reliability

来源：评论

学校读者我要写书评

暂无评论

History-Aware Online Cache Placement in Fog-Assisted IoT systems: An Integration of Learning and control

引用

IEEE internet OF THINGS JOURNAL 2021年第19期8卷 14683-14704页

作者： Gao, Xin Huang, Xi Tang, Yinxu Shao, Ziyu Yang, Yang ShanghaiTech Univ Sch Informat Sci & Technol Shanghai 201210 Peoples R China Chinese Acad Sci Shanghai Inst Microsyst & Informat Technol Shanghai 200050 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China ShanghaiTech Univ Shanghai Inst Fog Comp Technol Shanghai 201210 Peoples R China Peng Cheng Lab Res Ctr Network Commun Shenzhen 518000 Peoples R China Shenzhen SmartC Technol Dev Grp Co Ltd Shenzhen 518046 Peoples R China

In fog-assisted internet-of-Things systems, it is a common practice to cache popular content at the network edge to achieve high quality of service. Due to uncertainties, in practice, such as unknown file popularities, the cache placement scheme design is still an open problem with unresolved challenges: 1) how to maintain time-averaged storage costs under budgets;2) how to incorporate online learning to aid cache placement to minimize performance loss [also known as (a.k.a.) regret];and 3) how to exploit offline historical information to further reduce regret. In this article, we formulate the cache placement problem with unknown file popularities as a constrained combinatorial multiarmed bandit problem. To solve the problem, we employ virtual queue techniques to manage time-averaged storage cost constraints, and adopt history-aware bandit learning methods to integrate offline historical information into the online learning procedure to handle the exploration-exploitation tradeoff. With an effective combination of online control and history-aware online learning, we devise a cache placement scheme with history-aware bandit learning called CPHBL. Our theoretical analysis and simulations show that CPHBL achieves a sublinear time-averaged regret bound. Moreover, the simulation results verify CPHBL's advantage over the deep reinforcement learning-based approach.

关键词： internet of Things Wireless communication Delays Task analysis Uncertainty Servers Measurement Fog computing history-aware bandit learning internet of Things (IoT) learning-aided online control proactive caching

来源：评论

学校读者我要写书评

暂无评论

Power quality Disturbance Classification Using Transformer network 1st

Power Quality Disturbance Classification Using Transformer N...

引用

1st International conference on Cyber Warfare, Security and Space Research, SpacSec 2021

作者： Chiam, Dar Hung Lim, King Hann Curtin University Malaysia CDT 250 Sarawak Miri98009 Malaysia

ISBN: (纸本)9783031157837

The quality of power supplies has become an increasingly important subject in ensuring smooth operations of advanced instruments, especially in smart grid systems. Wide range of non-linear loads and advanced power electronics are connected to the grid causing abrupt power quality disturbances (PQD). Constant monitoring using machine intelligence can activate automate control of PQD detection and classification. In this paper, a transformer network is proposed to substitute the Long short-term memory (LSTM) network by tackling the problem of sequential processing while performing automatic time-series PQD classification. The aim of this paper is to provide a direct comparison of the multiple PQD classification performance between LSTM and transformer network. The training performance using noisy and noiseless signal are tested under several signal-to-noise ratio. In addition, three unknown noises are used to evaluate the model generalization towards noises that are not seen during training phase. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Fusion Modeling and Heterogeneous Simulation of Big Data Technology in 5G Communication network 4

Fusion Modeling and Heterogeneous Simulation of Big Data Tec...

引用

4th International conference on Smart systems and Inventive Technology, ICSSIT 2022

作者： Liu, Taiwei Wang, Caifeng Fu, Haiyan Lei, Tengfei Qilu Institute of Technology Shandong Jinan250000 China

ISBN: (纸本)9781665401180

In order to continuously improve the service capabilities of the 5G communication network and promote the formation of a high-quality and efficient service structure, the R&D team and technical personnel have gradually tried to apply big data technology to the 5G communication network and achieved certain results. In this context, the article takes the application of big data technology as a starting point, systematically discusses the application method of big data technology in 5G communication network, and studies the integration modeling and heterogeneous simulation of big data technology in 5G communication network based on deep learning. The simulation results show that the heterogeneous network improves big data by 6.6%. © 2022 IEEE

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：